Related papers: Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning

Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning

URL: http://arxiv.org/abs/2608.12108v2
Date: Thu, 13 Aug 2026 07:52:16 GMT
Title: Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning
Abstract summary: Federated learning enables collaborative model training across distributed clients while keeping data local.<n>A central challenge is determining which client updates are beneficial for aggregation with respect to each client's target domain.<n>We propose a federated learning framework that performs update selection in function space.
Score: 1.3924112497839525
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Federated learning (FL) enables collaborative model training across distributed clients while keeping data local. A central challenge is determining which client updates are beneficial for aggregation with respect to each client's target domain. Existing methods typically address this problem in parameter space by comparing model parameters or gradients. However, parameter-space similarity can be a poor proxy for predictive behavior, especially under heterogeneous, non-IID data. Consequently, updates that are misaligned with a client's target domain, including those caused by heterogeneous data or malfunctioning clients, may degrade local model performance. We propose Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR), a federated learning framework that performs update selection in function space. LIGHTYEAR uses an NTK-based agreement score to characterize predictive behavior and determine a personalized aggregation set for each client. By relating model parameters to local predictive responses, the Neural Tangent Kernel (NTK) provides a more expressive criterion for update selection than parameter-space similarity alone. Because function-space information is not available before aggregation in conventional centralized FL, LIGHTYEAR uses a peer-to-peer (P2P) topology in which clients exchange updates directly and evaluate incoming models on private validation data. Each client selects only updates that are beneficial for its own target domain and aggregates them using a regularized rule that improves stability under heterogeneity. Across five datasets and nine baseline methods, LIGHTYEAR consistently outperforms centralized FL baselines and existing P2P approaches.

Related papers

CRIP: Channel Level Representation Injection for Personalized One-Shot Federated Learning [10.225304989678202]
One-shot federated learning (OSFL) has emerged as a promising collaborative model learning framework with only a single round of communication.<n>We propose CRIP, a personalized OSFL framework that operates in the representation space via channel-level feature alignment.
arXiv Detail & Related papers (2026-08-03T13:41:07Z)
Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance.<n>We propose MoR, a federated alignment framework that combines GRPO with Mixture-of-Rewards for heterogeneousVLMs.<n>MoR consistently outperforms federated alignment baselines in generalization and cross-client adaptability.
arXiv Detail & Related papers (2026-05-05T07:02:50Z)
Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
We argue that replacing parameters with preferences represents a more scalable and privacy-preserving future.<n>We propose MoR, a federated alignment framework based on GRPO with Mixture-of-Rewards for heterogeneous VLMs.<n>MoR consistently outperforms federated alignment baselines in generalization, robustness, and cross-client adaptability.
arXiv Detail & Related papers (2026-01-31T03:11:51Z)
Federated Domain Generalization with Latent Space Inversion [42.37530136140609]
Federated domain generalization (FedDG) addresses distribution shifts among clients in a federated learning framework.<n>FedDG methods aggregate the parameters of locally trained client models to form a global model that generalizes to unseen clients while preserving data privacy.<n>Our solution addresses this problem by contributing new ways to perform local client training and model aggregation.
arXiv Detail & Related papers (2025-12-11T02:17:03Z)
CO-PFL: Contribution-Oriented Personalized Federated Learning for Heterogeneous Networks [51.43780477302533]
Contribution-Oriented PFL (CO-PFL) is a novel algorithm that dynamically estimates each client's contribution for global aggregation.<n>CO-PFL consistently surpasses state-of-the-art methods in robustness in personalization accuracy, robustness, scalability and convergence stability.
arXiv Detail & Related papers (2025-10-23T05:10:06Z)
Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning [1.3270838622986498]
Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy by keeping data local.<n>Traditional FL approaches rely on a centralized, star-shaped topology, where a central server aggregates model updates from clients.<n>We propose a decentralized, peer-to-peer (P2P) FL framework to enable each client to identify and aggregate a personalized set of trustworthy and beneficial updates.
arXiv Detail & Related papers (2025-08-07T10:10:37Z)
Client-Centric Federated Adaptive Optimization [78.30827455292827]
Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.<n>We propose Federated-Centric Adaptive Optimization, which is a class of novel federated optimization approaches.
arXiv Detail & Related papers (2025-01-17T04:00:50Z)
Enhancing Federated Learning with Adaptive Differential Privacy and Priority-Based Aggregation [0.0]
Federated learning (FL) develops global models without direct access to local datasets. It is possible to access the model updates transferred between clients and servers, potentially revealing sensitive local information to adversaries. Differential privacy (DP) offers a promising approach to addressing this issue by adding noise to the parameters. We propose a personalized DP framework that injects noise based on clients' relative impact factors and aggregates parameters.
arXiv Detail & Related papers (2024-06-26T16:55:07Z)
PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
arXiv Detail & Related papers (2024-06-04T13:51:08Z)
Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
arXiv Detail & Related papers (2023-05-01T20:04:46Z)
Adaptive Federated Learning via New Entropy Approach [14.595709494370372]
Federated Learning (FL) has emerged as a prominent distributed machine learning framework. In this paper, we propose an adaptive FEDerated learning algorithm based on ENTropy theory (FedEnt) to alleviate the parameter deviation among heterogeneous clients.
arXiv Detail & Related papers (2023-03-27T07:57:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.